diff --git a/.gitattributes b/.gitattributes index e9e8ef7e5dee8a0bd044d1852d4571c978662c6a..45b1ef8a9846f9eb289d655b3d37b69835392c92 100644 --- a/.gitattributes +++ b/.gitattributes @@ -5325,3 +5325,20 @@ neuronxcc-2.21.18209.0+043b1bf7/MODULE_7857c254fa9a7edf3a37+877608f3/model.neff neuronxcc-2.21.18209.0+043b1bf7/MODULE_0e70ec9049ca26a7f0f6+ed72d204/model.neff filter=lfs diff=lfs merge=lfs -text neuronxcc-2.21.18209.0+043b1bf7/MODULE_a2547d4e8c084e5503d9+a9d440f5/model.neff filter=lfs diff=lfs merge=lfs -text neuronxcc-2.21.18209.0+043b1bf7/MODULE_a2547d4e8c084e5503d9+a9d440f5/wrapped_neff.hlo filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.21.18209.0+043b1bf7/MODULE_25875318cd34a8c6e738+877608f3/model.neff filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.21.18209.0+043b1bf7/MODULE_3360dfdbc9cf20ffe3ea+a9d440f5/model.neff filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.21.18209.0+043b1bf7/MODULE_3360dfdbc9cf20ffe3ea+a9d440f5/wrapped_neff.hlo filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.21.18209.0+043b1bf7/MODULE_37ea567947fdd135736d+747527b0/model.neff filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.21.18209.0+043b1bf7/MODULE_37ea567947fdd135736d+747527b0/wrapped_neff.hlo filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.21.18209.0+043b1bf7/MODULE_4e93fdf5154aebbd1ec7+ed72d204/model.neff filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.21.18209.0+043b1bf7/MODULE_b9a7f9714b4d59f5ca3a+ed72d204/model.neff filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.21.18209.0+043b1bf7/MODULE_c94bb96d065f690fe53e+a9d440f5/model.neff filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.21.18209.0+043b1bf7/MODULE_c94bb96d065f690fe53e+a9d440f5/wrapped_neff.hlo filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.21.18209.0+043b1bf7/MODULE_daf3f26f1dd6b6a7b205/text_encoder/model.neuron filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.21.18209.0+043b1bf7/MODULE_daf3f26f1dd6b6a7b205/transformer/model.neuron filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.21.18209.0+043b1bf7/MODULE_daf3f26f1dd6b6a7b205/vae_decoder/model.neuron filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.21.18209.0+043b1bf7/MODULE_daf3f26f1dd6b6a7b205/vae_encoder/model.neuron filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.21.18209.0+043b1bf7/MODULE_e1858108239cd6fa94e5+34ec65ed/model.neff filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.21.18209.0+043b1bf7/MODULE_e1858108239cd6fa94e5+34ec65ed/wrapped_neff.hlo filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.21.18209.0+043b1bf7/MODULE_ec01adc6d76b4d3733bc+cdc6a67b/model.neff filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.21.18209.0+043b1bf7/MODULE_ec01adc6d76b4d3733bc+cdc6a67b/wrapped_neff.hlo filter=lfs diff=lfs merge=lfs -text diff --git a/neuronxcc-2.21.18209.0+043b1bf7/0_REGISTRY/0.4.1.dev0/diffusion-transformer/PixArt-alpha/PixArt-XL-2-512x512/daf3f26f1dd6b6a7b205.json b/neuronxcc-2.21.18209.0+043b1bf7/0_REGISTRY/0.4.1.dev0/diffusion-transformer/PixArt-alpha/PixArt-XL-2-512x512/daf3f26f1dd6b6a7b205.json new file mode 100644 index 0000000000000000000000000000000000000000..8e677cb8b57e29c3ff3a2d0e4dba187badd5c518 --- /dev/null +++ b/neuronxcc-2.21.18209.0+043b1bf7/0_REGISTRY/0.4.1.dev0/diffusion-transformer/PixArt-alpha/PixArt-XL-2-512x512/daf3f26f1dd6b6a7b205.json @@ -0,0 +1,102 @@ +{ + "_entry_class": "MultiModelCacheEntry", + "_model_id": "PixArt-alpha/PixArt-XL-2-512x512", + "_task": null, + "text_encoder": { + "architectures": [ + "T5EncoderModel" + ], + "classifier_dropout": 0.0, + "d_ff": 10240, + "d_kv": 64, + "d_model": 4096, + "decoder_start_token_id": 0, + "dense_act_fn": "gelu_new", + "dropout_rate": 0.1, + "export_model_type": "t5-encoder", + "feed_forward_proj": "gated-gelu", + "initializer_factor": 1.0, + "is_encoder_decoder": false, + "is_gated_act": true, + "layer_norm_epsilon": 1e-06, + "model_type": "t5", + "neuron": { + "auto_cast": null, + "auto_cast_type": null, + "compiler_type": "neuronx-cc", + "compiler_version": "2.21.18209.0+043b1bf7", + "dynamic_batch_size": false, + "float_dtype": "fp32", + "inline_weights_to_neff": false, + "instance_type": "trn1", + "int_dtype": "int64", + "optlevel": "2", + "output_attentions": false, + "output_hidden_states": false, + "static_batch_size": 1, + "static_sequence_length": 120, + "task": "feature-extraction", + "tensor_parallel_size": 1 + }, + "num_decoder_layers": 24, + "num_heads": 64, + "num_layers": 24, + "output_past": true, + "relative_attention_max_distance": 128, + "relative_attention_num_buckets": 32, + "tie_word_embeddings": false, + "use_cache": false, + "vocab_size": 32128 + }, + "transformer": { + "_class_name": "PixArtTransformer2DModel", + "activation_fn": "gelu-approximate", + "attention_bias": true, + "attention_head_dim": 72, + "attention_type": "default", + "caption_channels": 4096, + "cross_attention_dim": 1152, + "double_self_attention": false, + "dropout": 0.0, + "in_channels": 4, + "interpolation_scale": null, + "neuron": { + "auto_cast": null, + "auto_cast_type": null, + "compiler_type": "neuronx-cc", + "compiler_version": "2.21.18209.0+043b1bf7", + "dynamic_batch_size": false, + "float_dtype": "bf16", + "inline_weights_to_neff": false, + "instance_type": "trn1", + "int_dtype": "int64", + "optlevel": "2", + "output_attentions": false, + "output_hidden_states": false, + "static_batch_size": 1, + "static_encoder_hidden_size": 4096, + "static_height": 64, + "static_num_channels": 4, + "static_sequence_length": 120, + "static_vae_scale_factor": 8, + "static_width": 64, + "task": "semantic-segmentation", + "tensor_parallel_size": 1 + }, + "norm_elementwise_affine": false, + "norm_eps": 1e-06, + "norm_num_groups": 32, + "norm_type": "ada_norm_single", + "num_attention_heads": 16, + "num_embeds_ada_norm": 1000, + "num_layers": 28, + "num_vector_embeds": null, + "only_cross_attention": false, + "out_channels": 8, + "output_attentions": false, + "patch_size": 2, + "upcast_attention": false, + "use_additional_conditions": null, + "use_linear_projection": false + } +} \ No newline at end of file diff --git a/neuronxcc-2.21.18209.0+043b1bf7/0_REGISTRY/0.4.1.dev0/llama/llamafactory/tiny-random-Llama-3/66509396a74c016d41b0.json b/neuronxcc-2.21.18209.0+043b1bf7/0_REGISTRY/0.4.1.dev0/llama/llamafactory/tiny-random-Llama-3/66509396a74c016d41b0.json new file mode 100644 index 0000000000000000000000000000000000000000..d8b2da1842b8dfc9b1fe45d25c06a836feb29347 --- /dev/null +++ b/neuronxcc-2.21.18209.0+043b1bf7/0_REGISTRY/0.4.1.dev0/llama/llamafactory/tiny-random-Llama-3/66509396a74c016d41b0.json @@ -0,0 +1,62 @@ +{ + "_entry_class": "SingleModelCacheEntry", + "_model_id": "llamafactory/tiny-random-Llama-3", + "_task": "text-generation", + "architectures": [ + "LlamaForCausalLM" + ], + "attention_bias": false, + "attention_dropout": 0.0, + "head_dim": 4, + "hidden_act": "silu", + "hidden_size": 16, + "initializer_range": 0.02, + "intermediate_size": 64, + "max_position_embeddings": 131072, + "mlp_bias": false, + "model_type": "llama", + "neuron": { + "_serialized_key": "NxDNeuronConfig", + "batch_size": 2, + "capacity_factor": null, + "checkpoint_id": "llamafactory/tiny-random-Llama-3", + "checkpoint_revision": "bf2a2e3bf199ad2ee96f02a3c00246c608db22a8", + "continuous_batching": true, + "enable_bucketing": false, + "ep_degree": 1, + "fused_qkv": true, + "glu_mlp": true, + "local_ranks_size": 2, + "max_batch_size": 2, + "max_context_length": 128, + "max_topk": 256, + "n_active_tokens": 128, + "neuronxcc_version": "2.21.18209.0+043b1bf7", + "on_device_sampling": true, + "optimum_neuron_version": "0.4.1.dev0", + "output_logits": false, + "pp_degree": 1, + "sequence_length": 128, + "speculation_length": 0, + "start_rank_id": 0, + "target": "trn1", + "torch_dtype": "float16", + "tp_degree": 2 + }, + "num_attention_heads": 4, + "num_hidden_layers": 2, + "num_key_value_heads": 4, + "pretraining_tp": 1, + "rms_norm_eps": 1e-05, + "rope_scaling": { + "factor": 8.0, + "high_freq_factor": 4.0, + "low_freq_factor": 1.0, + "original_max_position_embeddings": 8192, + "rope_type": "llama3" + }, + "rope_theta": 500000.0, + "tie_word_embeddings": false, + "use_cache": true, + "vocab_size": 128256 +} \ No newline at end of file diff --git a/neuronxcc-2.21.18209.0+043b1bf7/0_REGISTRY/0.4.1.dev0/llama/llamafactory/tiny-random-Llama-3/a0df19da9c3c531250d2.json b/neuronxcc-2.21.18209.0+043b1bf7/0_REGISTRY/0.4.1.dev0/llama/llamafactory/tiny-random-Llama-3/a0df19da9c3c531250d2.json new file mode 100644 index 0000000000000000000000000000000000000000..9c640f09a4e70b062c3e43b3d8c760bbde625665 --- /dev/null +++ b/neuronxcc-2.21.18209.0+043b1bf7/0_REGISTRY/0.4.1.dev0/llama/llamafactory/tiny-random-Llama-3/a0df19da9c3c531250d2.json @@ -0,0 +1,62 @@ +{ + "_entry_class": "SingleModelCacheEntry", + "_model_id": "llamafactory/tiny-random-Llama-3", + "_task": "text-generation", + "architectures": [ + "LlamaForCausalLM" + ], + "attention_bias": false, + "attention_dropout": 0.0, + "head_dim": 4, + "hidden_act": "silu", + "hidden_size": 16, + "initializer_range": 0.02, + "intermediate_size": 64, + "max_position_embeddings": 131072, + "mlp_bias": false, + "model_type": "llama", + "neuron": { + "_serialized_key": "NxDNeuronConfig", + "batch_size": 2, + "capacity_factor": null, + "checkpoint_id": "llamafactory/tiny-random-Llama-3", + "checkpoint_revision": "bf2a2e3bf199ad2ee96f02a3c00246c608db22a8", + "continuous_batching": true, + "enable_bucketing": false, + "ep_degree": 1, + "fused_qkv": true, + "glu_mlp": true, + "local_ranks_size": 2, + "max_batch_size": 2, + "max_context_length": 128, + "max_topk": 256, + "n_active_tokens": 128, + "neuronxcc_version": "2.21.18209.0+043b1bf7", + "on_device_sampling": true, + "optimum_neuron_version": "0.4.1.dev0", + "output_logits": false, + "pp_degree": 1, + "sequence_length": 128, + "speculation_length": 0, + "start_rank_id": 0, + "target": "trn2", + "torch_dtype": "float16", + "tp_degree": 2 + }, + "num_attention_heads": 4, + "num_hidden_layers": 2, + "num_key_value_heads": 4, + "pretraining_tp": 1, + "rms_norm_eps": 1e-05, + "rope_scaling": { + "factor": 8.0, + "high_freq_factor": 4.0, + "low_freq_factor": 1.0, + "original_max_position_embeddings": 8192, + "rope_type": "llama3" + }, + "rope_theta": 500000.0, + "tie_word_embeddings": false, + "use_cache": true, + "vocab_size": 128256 +} \ No newline at end of file diff --git a/neuronxcc-2.21.18209.0+043b1bf7/0_REGISTRY/0.4.1.dev0/qwen3/Qwen/Qwen3-0.6B/9a3f48228cf1a10a6db2.json b/neuronxcc-2.21.18209.0+043b1bf7/0_REGISTRY/0.4.1.dev0/qwen3/Qwen/Qwen3-0.6B/9a3f48228cf1a10a6db2.json new file mode 100644 index 0000000000000000000000000000000000000000..12b40f08dd18b674d6a7427789acf8b60181007e --- /dev/null +++ b/neuronxcc-2.21.18209.0+043b1bf7/0_REGISTRY/0.4.1.dev0/qwen3/Qwen/Qwen3-0.6B/9a3f48228cf1a10a6db2.json @@ -0,0 +1,87 @@ +{ + "_entry_class": "SingleModelCacheEntry", + "_model_id": "Qwen/Qwen3-0.6B", + "_task": "text-generation", + "architectures": [ + "Qwen3ForCausalLM" + ], + "attention_bias": false, + "attention_dropout": 0.0, + "head_dim": 128, + "hidden_act": "silu", + "hidden_size": 1024, + "initializer_range": 0.02, + "intermediate_size": 3072, + "layer_types": [ + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention" + ], + "max_position_embeddings": 40960, + "max_window_layers": 28, + "model_type": "qwen3", + "neuron": { + "_serialized_key": "NxDNeuronConfig", + "batch_size": 1, + "capacity_factor": null, + "checkpoint_id": "Qwen/Qwen3-0.6B", + "checkpoint_revision": "c1899de289a04d12100db370d81485cdf75e47ca", + "continuous_batching": false, + "enable_bucketing": false, + "ep_degree": 1, + "fused_qkv": true, + "glu_mlp": true, + "local_ranks_size": 2, + "max_batch_size": 1, + "max_context_length": 4096, + "max_topk": 256, + "n_active_tokens": 4096, + "neuronxcc_version": "2.21.18209.0+043b1bf7", + "on_device_sampling": true, + "optimum_neuron_version": "0.4.1.dev0", + "output_logits": false, + "pp_degree": 1, + "sequence_length": 4096, + "speculation_length": 0, + "start_rank_id": 0, + "target": "trn1", + "torch_dtype": "bfloat16", + "tp_degree": 2 + }, + "num_attention_heads": 16, + "num_hidden_layers": 28, + "num_key_value_heads": 8, + "rms_norm_eps": 1e-06, + "rope_scaling": null, + "rope_theta": 1000000, + "sliding_window": null, + "tie_word_embeddings": true, + "use_cache": true, + "use_sliding_window": false, + "vocab_size": 151936 +} \ No newline at end of file diff --git a/neuronxcc-2.21.18209.0+043b1bf7/0_REGISTRY/0.4.1.dev0/qwen3/Qwen/Qwen3-Embedding-0.6B/bda840f20094d5c6f760.json b/neuronxcc-2.21.18209.0+043b1bf7/0_REGISTRY/0.4.1.dev0/qwen3/Qwen/Qwen3-Embedding-0.6B/bda840f20094d5c6f760.json new file mode 100644 index 0000000000000000000000000000000000000000..f0364de250a3d475d0a45bdd66fb0eb35cdf26a3 --- /dev/null +++ b/neuronxcc-2.21.18209.0+043b1bf7/0_REGISTRY/0.4.1.dev0/qwen3/Qwen/Qwen3-Embedding-0.6B/bda840f20094d5c6f760.json @@ -0,0 +1,87 @@ +{ + "_entry_class": "SingleModelCacheEntry", + "_model_id": "Qwen/Qwen3-Embedding-0.6B", + "_task": "text-generation", + "architectures": [ + "Qwen3ForCausalLM" + ], + "attention_bias": false, + "attention_dropout": 0.0, + "head_dim": 128, + "hidden_act": "silu", + "hidden_size": 1024, + "initializer_range": 0.02, + "intermediate_size": 3072, + "layer_types": [ + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention" + ], + "max_position_embeddings": 32768, + "max_window_layers": 28, + "model_type": "qwen3", + "neuron": { + "_serialized_key": "NxDNeuronConfig", + "batch_size": 1, + "capacity_factor": null, + "checkpoint_id": "Qwen/Qwen3-Embedding-0.6B", + "checkpoint_revision": "c54f2e6e80b2d7b7de06f51cec4959f6b3e03418", + "continuous_batching": false, + "enable_bucketing": false, + "ep_degree": 1, + "fused_qkv": true, + "glu_mlp": true, + "local_ranks_size": 1, + "max_batch_size": 1, + "max_context_length": 1024, + "max_topk": 256, + "n_active_tokens": 1024, + "neuronxcc_version": "2.21.18209.0+043b1bf7", + "on_device_sampling": false, + "optimum_neuron_version": "0.4.1.dev0", + "output_logits": false, + "pp_degree": 1, + "sequence_length": 1024, + "speculation_length": 0, + "start_rank_id": 0, + "target": "trn1", + "torch_dtype": "bfloat16", + "tp_degree": 1 + }, + "num_attention_heads": 16, + "num_hidden_layers": 28, + "num_key_value_heads": 8, + "rms_norm_eps": 1e-06, + "rope_scaling": null, + "rope_theta": 1000000, + "sliding_window": null, + "tie_word_embeddings": true, + "use_cache": true, + "use_sliding_window": false, + "vocab_size": 151669 +} \ No newline at end of file diff --git a/neuronxcc-2.21.18209.0+043b1bf7/MODULE_0dc4bd0a16b1a4ab1733+c2248236/model.hlo_module.pb b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_0dc4bd0a16b1a4ab1733+c2248236/model.hlo_module.pb index 0b8a01fc6954df312e1b05b385ad2de26c39deff..380e691f108e93e00dd9e9bf0b9bc3a6e14db163 100644 --- a/neuronxcc-2.21.18209.0+043b1bf7/MODULE_0dc4bd0a16b1a4ab1733+c2248236/model.hlo_module.pb +++ b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_0dc4bd0a16b1a4ab1733+c2248236/model.hlo_module.pb @@ -1,3 +1,3 @@ version https://git-lfs.github.com/spec/v1 -oid sha256:017fd1b59af56e134a8f3ae77b50bce4960bf820c2291967f002dc627a69a99f +oid sha256:61586b49e1e903cab9fff0482909f040c5e97621b59f6233899973b7cd27184d size 84807 diff --git a/neuronxcc-2.21.18209.0+043b1bf7/MODULE_0dc4bd0a16b1a4ab1733+c2248236/model.neff b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_0dc4bd0a16b1a4ab1733+c2248236/model.neff index 5dcf202ae4a188bab73a6cf678b7a47b679efe62..4c1e306ee3a3e27778fd522f49edef71ad85925d 100644 --- a/neuronxcc-2.21.18209.0+043b1bf7/MODULE_0dc4bd0a16b1a4ab1733+c2248236/model.neff +++ b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_0dc4bd0a16b1a4ab1733+c2248236/model.neff @@ -1,3 +1,3 @@ version https://git-lfs.github.com/spec/v1 -oid sha256:6197fd677022e4562f06c9013a1ea531d8c0b4822263cec87758f73893cbc883 +oid sha256:a33b221d4039eaaa99cb40b84d626d05299fe802098783ac5418f3b32574abe8 size 646144 diff --git a/neuronxcc-2.21.18209.0+043b1bf7/MODULE_13aa568fe38435861b30+a9d440f5/model.neff b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_13aa568fe38435861b30+a9d440f5/model.neff index 95596fc75f69d935945238d5fea0228c1fdcb7c7..4b73f8be39b0687e66c93f803551ed1a14d785fe 100644 --- a/neuronxcc-2.21.18209.0+043b1bf7/MODULE_13aa568fe38435861b30+a9d440f5/model.neff +++ b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_13aa568fe38435861b30+a9d440f5/model.neff @@ -1,3 +1,3 @@ version https://git-lfs.github.com/spec/v1 -oid sha256:995dde6558ec218034ee6bfadb9001d15666f60d47e1bfb96959c4374f4a5160 +oid sha256:a2d9f3177230710833e1a22c473ceb0215149d4996fb169ded5f87e0ebd9b6e7 size 246784 diff --git a/neuronxcc-2.21.18209.0+043b1bf7/MODULE_13aa568fe38435861b30+a9d440f5/wrapped_neff.hlo b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_13aa568fe38435861b30+a9d440f5/wrapped_neff.hlo index 0baf4725bcf246def47cab9ec1a05eae88c3f984..6947b23b1665a11411eff49c5a64caa7c8eb0fda 100644 --- a/neuronxcc-2.21.18209.0+043b1bf7/MODULE_13aa568fe38435861b30+a9d440f5/wrapped_neff.hlo +++ b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_13aa568fe38435861b30+a9d440f5/wrapped_neff.hlo @@ -1,3 +1,3 @@ version https://git-lfs.github.com/spec/v1 -oid sha256:c965d92c0838f2172d1ce99ae28e8b19fe85df43e821f94e31751dec2b5e4af3 +oid sha256:11296a74882475c7e044dddae990ac1e06a377d292f8bbbabccbf9f52a68de87 size 255104 diff --git a/neuronxcc-2.21.18209.0+043b1bf7/MODULE_198eb3e5a6d933feebd0+ed72d204/model.hlo_module.pb b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_198eb3e5a6d933feebd0+ed72d204/model.hlo_module.pb index 2cbe5bb347d2a83789a6b580e4cd607e95c6b144..71cc5af4454da4b12e5b11d5a5cd0c9f1768fe1d 100644 --- a/neuronxcc-2.21.18209.0+043b1bf7/MODULE_198eb3e5a6d933feebd0+ed72d204/model.hlo_module.pb +++ b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_198eb3e5a6d933feebd0+ed72d204/model.hlo_module.pb @@ -1,3 +1,3 @@ version https://git-lfs.github.com/spec/v1 -oid sha256:b2aaa679a020415ee5b0946c6980026f3673ecebec68d8bd20e9a1e942b71265 +oid sha256:010699d8fe7fd543b752b93c8bc2cd72e5309050ab149427dfd589c97e7268c5 size 81516 diff --git a/neuronxcc-2.21.18209.0+043b1bf7/MODULE_198eb3e5a6d933feebd0+ed72d204/model.neff b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_198eb3e5a6d933feebd0+ed72d204/model.neff index 0e761765decdd10c771a725506d540f79e574bcf..1f401e6c73ae59741f109c92ca047d40bbced4d2 100644 --- a/neuronxcc-2.21.18209.0+043b1bf7/MODULE_198eb3e5a6d933feebd0+ed72d204/model.neff +++ b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_198eb3e5a6d933feebd0+ed72d204/model.neff @@ -1,3 +1,3 @@ version https://git-lfs.github.com/spec/v1 -oid sha256:9939f9bf1f6e046ae9968d2ddd8afa415064ae1d7bb0acbba84ef85296090aa3 +oid sha256:36bf12c475e30b9ae5c3e55dc492a5b36e2b84326264d9707f19e411d4862c1a size 267264 diff --git a/neuronxcc-2.21.18209.0+043b1bf7/MODULE_19f0ddffb404ac2b8204+253d6470/model.hlo_module.pb b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_19f0ddffb404ac2b8204+253d6470/model.hlo_module.pb index 59e9d0d2f89ef3c52d54dcee4217664bd6a5628e..fb9a088a70cc3ed35cd9c1c2443ce8f328cf694b 100644 --- a/neuronxcc-2.21.18209.0+043b1bf7/MODULE_19f0ddffb404ac2b8204+253d6470/model.hlo_module.pb +++ b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_19f0ddffb404ac2b8204+253d6470/model.hlo_module.pb @@ -1,3 +1,3 @@ version https://git-lfs.github.com/spec/v1 -oid sha256:8b9548012c66a27d1734252c9d5e13bebf8352e9b795d8395badbb16c34b4bb0 +oid sha256:e8c4af19c1f6118b30a135c4553925fc304a74428ae95971dcad784cdef2729b size 97794 diff --git a/neuronxcc-2.21.18209.0+043b1bf7/MODULE_19f0ddffb404ac2b8204+253d6470/model.neff b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_19f0ddffb404ac2b8204+253d6470/model.neff index 71ba766dd7592d48fd09e3496ddf36d85ce23b8d..0006b75ec7688b8ab09218e772eaaef6ed0176d2 100644 --- a/neuronxcc-2.21.18209.0+043b1bf7/MODULE_19f0ddffb404ac2b8204+253d6470/model.neff +++ b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_19f0ddffb404ac2b8204+253d6470/model.neff @@ -1,3 +1,3 @@ version https://git-lfs.github.com/spec/v1 -oid sha256:a8f073ed10513531bcaf542a905eb5d80704a541a1ea5cfc869af061504a489a +oid sha256:d3706159398be1c857cb9410baa841093252d4bd2db4a6ec6e5fcfcb5866e59d size 410624 diff --git a/neuronxcc-2.21.18209.0+043b1bf7/MODULE_1e1261ac026ac7064c12+ed72d204/model.hlo_module.pb b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_1e1261ac026ac7064c12+ed72d204/model.hlo_module.pb index 0208f3e5f9b717aa51bd94a5e2b7bde3e1051920..4e048268a2ebda42a903d9c30e684be97aec650d 100644 --- a/neuronxcc-2.21.18209.0+043b1bf7/MODULE_1e1261ac026ac7064c12+ed72d204/model.hlo_module.pb +++ b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_1e1261ac026ac7064c12+ed72d204/model.hlo_module.pb @@ -1,3 +1,3 @@ version https://git-lfs.github.com/spec/v1 -oid sha256:41cc515d48e8260f02395a97fb96cf882b6bbd63dd1e0459ca611c93200db368 +oid sha256:42d1111cccd29ce4edd640c6b5880fa7b920b5c1211396da06d3b58670ec7a12 size 90382 diff --git a/neuronxcc-2.21.18209.0+043b1bf7/MODULE_1e1261ac026ac7064c12+ed72d204/model.neff b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_1e1261ac026ac7064c12+ed72d204/model.neff index 86174f434707ce5d3013df3ca5c876422a1046a3..fde2255bdb0c89a5a5638df492a98fed01c7aaef 100644 --- a/neuronxcc-2.21.18209.0+043b1bf7/MODULE_1e1261ac026ac7064c12+ed72d204/model.neff +++ b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_1e1261ac026ac7064c12+ed72d204/model.neff @@ -1,3 +1,3 @@ version https://git-lfs.github.com/spec/v1 -oid sha256:c11a3ad3c54f42fd4888286b0d1a3dc80638dfc20a5001b3d0166c89a0f84e5b +oid sha256:e07848927e2ef873e5477430034ef70cac7c7af77f9e216a81255e421762ed85 size 359424 diff --git a/neuronxcc-2.21.18209.0+043b1bf7/MODULE_25875318cd34a8c6e738+877608f3/compile_flags.json b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_25875318cd34a8c6e738+877608f3/compile_flags.json new file mode 100644 index 0000000000000000000000000000000000000000..fc27c67e0f3bd30aba010defcc6c2d0646e87b83 --- /dev/null +++ b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_25875318cd34a8c6e738+877608f3/compile_flags.json @@ -0,0 +1 @@ +["--target=trn2", "--auto-cast=none", "--model-type=transformer", "--tensorizer-options=--enable-ccop-compute-overlap --cc-pipeline-tiling-factor=2 --vectorize-strided-dma ", "-O2", "--lnc=2", "--logfile=/tmp/nxd_model/context_encoding_model/_tp0_bk0/log-neuron-cc.txt"] \ No newline at end of file diff --git a/neuronxcc-2.21.18209.0+043b1bf7/MODULE_25875318cd34a8c6e738+877608f3/model.done b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_25875318cd34a8c6e738+877608f3/model.done new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/neuronxcc-2.21.18209.0+043b1bf7/MODULE_25875318cd34a8c6e738+877608f3/model.hlo_module.pb b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_25875318cd34a8c6e738+877608f3/model.hlo_module.pb new file mode 100644 index 0000000000000000000000000000000000000000..cd2d403570fee6c3a24497e6f1bd4526be9448d9 --- /dev/null +++ b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_25875318cd34a8c6e738+877608f3/model.hlo_module.pb @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:98a176554451485ee2e3396bd66f6314c482af73ae61ff4b5a2b90786765a642 +size 1289358 diff --git a/neuronxcc-2.21.18209.0+043b1bf7/MODULE_25875318cd34a8c6e738+877608f3/model.neff b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_25875318cd34a8c6e738+877608f3/model.neff new file mode 100644 index 0000000000000000000000000000000000000000..98587862d622a196eb84d8ef7673efc73575705d --- /dev/null +++ b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_25875318cd34a8c6e738+877608f3/model.neff @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f091182eeac4dcf274fb36008a9da3f4ae0df8e42294735025761bc95389713c +size 728064 diff --git a/neuronxcc-2.21.18209.0+043b1bf7/MODULE_3360dfdbc9cf20ffe3ea+a9d440f5/compile_flags.json b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_3360dfdbc9cf20ffe3ea+a9d440f5/compile_flags.json new file mode 100644 index 0000000000000000000000000000000000000000..34675115220079309bfad2d45680c478c378a3c0 --- /dev/null +++ b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_3360dfdbc9cf20ffe3ea+a9d440f5/compile_flags.json @@ -0,0 +1 @@ +["--target=trn1", "--auto-cast=none", "--model-type=transformer", "--tensorizer-options=--enable-ccop-compute-overlap --cc-pipeline-tiling-factor=2 --vectorize-strided-dma ", "-O2", "--lnc=1", "--logfile=/tmp/nxd_model/token_generation_model/_tp0_bk0/log-neuron-cc.txt", "--enable-internal-neff-wrapper"] \ No newline at end of file diff --git a/neuronxcc-2.21.18209.0+043b1bf7/MODULE_3360dfdbc9cf20ffe3ea+a9d440f5/model.done b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_3360dfdbc9cf20ffe3ea+a9d440f5/model.done new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/neuronxcc-2.21.18209.0+043b1bf7/MODULE_3360dfdbc9cf20ffe3ea+a9d440f5/model.hlo_module.pb b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_3360dfdbc9cf20ffe3ea+a9d440f5/model.hlo_module.pb new file mode 100644 index 0000000000000000000000000000000000000000..f8a17cd08c6a504ae7d0fd64b6823290f002a0ba --- /dev/null +++ b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_3360dfdbc9cf20ffe3ea+a9d440f5/model.hlo_module.pb @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7d27d563a4e3028e4ea49838d9c3b5f1557c20ff9dd0f09d8fc5f9c669102fbe +size 658192 diff --git a/neuronxcc-2.21.18209.0+043b1bf7/MODULE_3360dfdbc9cf20ffe3ea+a9d440f5/model.neff b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_3360dfdbc9cf20ffe3ea+a9d440f5/model.neff new file mode 100644 index 0000000000000000000000000000000000000000..ad21d7119da25bd9da999474f45924b612934dbe --- /dev/null +++ b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_3360dfdbc9cf20ffe3ea+a9d440f5/model.neff @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1e6bd5080e30cb75bdd6b2157daeb16e6c52ad35e65ccdaa0a523408517ec0ea +size 1915904 diff --git a/neuronxcc-2.21.18209.0+043b1bf7/MODULE_3360dfdbc9cf20ffe3ea+a9d440f5/wrapped_neff.hlo b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_3360dfdbc9cf20ffe3ea+a9d440f5/wrapped_neff.hlo new file mode 100644 index 0000000000000000000000000000000000000000..278bd42d9daa3a479d8f18300698bd079bf2eff9 --- /dev/null +++ b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_3360dfdbc9cf20ffe3ea+a9d440f5/wrapped_neff.hlo @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:78a5ae8a75a3a4e0656c3937dc2bec0710df3820ba3db609ff551cf806a50c75 +size 2053551 diff --git a/neuronxcc-2.21.18209.0+043b1bf7/MODULE_37ea567947fdd135736d+747527b0/compile_flags.json b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_37ea567947fdd135736d+747527b0/compile_flags.json new file mode 100644 index 0000000000000000000000000000000000000000..8da50ffdebbe4b136d67d64bb87ac42d154163d7 --- /dev/null +++ b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_37ea567947fdd135736d+747527b0/compile_flags.json @@ -0,0 +1 @@ +["--target=trn2", "--auto-cast=none", "--model-type=transformer", "--tensorizer-options=--enable-ccop-compute-overlap --cc-pipeline-tiling-factor=2 --vectorize-strided-dma ", "-O2", "--lnc=2", "--logfile=/tmp/nxd_model/token_generation_model/_tp0_bk0/log-neuron-cc.txt", "--enable-internal-neff-wrapper"] \ No newline at end of file diff --git a/neuronxcc-2.21.18209.0+043b1bf7/MODULE_37ea567947fdd135736d+747527b0/model.done b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_37ea567947fdd135736d+747527b0/model.done new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/neuronxcc-2.21.18209.0+043b1bf7/MODULE_37ea567947fdd135736d+747527b0/model.hlo_module.pb b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_37ea567947fdd135736d+747527b0/model.hlo_module.pb new file mode 100644 index 0000000000000000000000000000000000000000..1bad6c386937e7badadc00a4bd6b595534498c80 --- /dev/null +++ b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_37ea567947fdd135736d+747527b0/model.hlo_module.pb @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c5d477f34ae752f5a59c170824b8b4808870f92b137ec5c4cf7cb18299e7a0c7 +size 1574268 diff --git a/neuronxcc-2.21.18209.0+043b1bf7/MODULE_37ea567947fdd135736d+747527b0/model.neff b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_37ea567947fdd135736d+747527b0/model.neff new file mode 100644 index 0000000000000000000000000000000000000000..b8ebbeb3f84b3b2dc4db1bd3573dcb4e7d022de6 --- /dev/null +++ b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_37ea567947fdd135736d+747527b0/model.neff @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3b439829eb058574688a6b0736453d69ba3ab5c982d01d54f5844d63908c6c31 +size 779264 diff --git a/neuronxcc-2.21.18209.0+043b1bf7/MODULE_37ea567947fdd135736d+747527b0/wrapped_neff.hlo b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_37ea567947fdd135736d+747527b0/wrapped_neff.hlo new file mode 100644 index 0000000000000000000000000000000000000000..c492f84d471efb1207ef25461f84a04a987dc30a --- /dev/null +++ b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_37ea567947fdd135736d+747527b0/wrapped_neff.hlo @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0e796f6271a547530c9625da1ca1b5155f4d2a3d2fb51f03fbb465adfa2554c4 +size 787211 diff --git a/neuronxcc-2.21.18209.0+043b1bf7/MODULE_4e93fdf5154aebbd1ec7+ed72d204/compile_flags.json b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_4e93fdf5154aebbd1ec7+ed72d204/compile_flags.json new file mode 100644 index 0000000000000000000000000000000000000000..1569eac18fc7f34b3fe66166f2d7a4a59dbc5aa4 --- /dev/null +++ b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_4e93fdf5154aebbd1ec7+ed72d204/compile_flags.json @@ -0,0 +1 @@ +["--target=trn1", "--auto-cast=none", "--model-type=transformer", "--tensorizer-options=--enable-ccop-compute-overlap --cc-pipeline-tiling-factor=2 --vectorize-strided-dma ", "-O2", "--lnc=1", "--logfile=/tmp/nxd_model/context_encoding_model/_tp0_bk0/log-neuron-cc.txt"] \ No newline at end of file diff --git a/neuronxcc-2.21.18209.0+043b1bf7/MODULE_4e93fdf5154aebbd1ec7+ed72d204/model.done b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_4e93fdf5154aebbd1ec7+ed72d204/model.done new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/neuronxcc-2.21.18209.0+043b1bf7/MODULE_4e93fdf5154aebbd1ec7+ed72d204/model.hlo_module.pb b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_4e93fdf5154aebbd1ec7+ed72d204/model.hlo_module.pb new file mode 100644 index 0000000000000000000000000000000000000000..19e4d5ae4b3cd857444eaf64a6ba7bd6f498acad --- /dev/null +++ b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_4e93fdf5154aebbd1ec7+ed72d204/model.hlo_module.pb @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c3312876ce41e0fcc32e5f19ddc83cfa44fe317d39b1f1aa97a6b21f49acbb23 +size 586051 diff --git a/neuronxcc-2.21.18209.0+043b1bf7/MODULE_4e93fdf5154aebbd1ec7+ed72d204/model.neff b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_4e93fdf5154aebbd1ec7+ed72d204/model.neff new file mode 100644 index 0000000000000000000000000000000000000000..1cc29860a288ab10650f92cc8572f76fe0b29daa --- /dev/null +++ b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_4e93fdf5154aebbd1ec7+ed72d204/model.neff @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f81219ec13b4f22f03d84b7a75fa54cf308d9910802fcaff32c3be93c0486790 +size 7097344 diff --git a/neuronxcc-2.21.18209.0+043b1bf7/MODULE_5949b466ee5d32903b5e+ca355898/model.neff b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_5949b466ee5d32903b5e+ca355898/model.neff index e9055915542a4950a725795843fc74a2f7317f09..389986f6420c8d5b0f98999feb0b5b86942d2cc5 100644 --- a/neuronxcc-2.21.18209.0+043b1bf7/MODULE_5949b466ee5d32903b5e+ca355898/model.neff +++ b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_5949b466ee5d32903b5e+ca355898/model.neff @@ -1,3 +1,3 @@ version https://git-lfs.github.com/spec/v1 -oid sha256:9167b7b2cd10069c278b83192fbb62e014bb7c1eb8594c71677648de956fdfdd +oid sha256:1c575672250d5f23841d008ced6c33f1df62b6d57923b8be0b7797455ae58cf2 size 277504 diff --git a/neuronxcc-2.21.18209.0+043b1bf7/MODULE_5949b466ee5d32903b5e+ca355898/wrapped_neff.hlo b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_5949b466ee5d32903b5e+ca355898/wrapped_neff.hlo index e712d27b589755fd5baa4233f2a0e5b0ccfc8ec3..617ded72a276d7638fe3fa89d291e1dc6af446a3 100644 --- a/neuronxcc-2.21.18209.0+043b1bf7/MODULE_5949b466ee5d32903b5e+ca355898/wrapped_neff.hlo +++ b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_5949b466ee5d32903b5e+ca355898/wrapped_neff.hlo @@ -1,3 +1,3 @@ version https://git-lfs.github.com/spec/v1 -oid sha256:b744dda98cd03803c365f911815c08eeee3aad06d05eafe96e00f28e9f06e3de +oid sha256:f05228c5d86d72717d585b6556529ede68ef62b4a306d5d7bfaf5f07ef7d9d96 size 289571 diff --git a/neuronxcc-2.21.18209.0+043b1bf7/MODULE_a6ac71f9922f4f01abf5+a9d440f5/model.neff b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_a6ac71f9922f4f01abf5+a9d440f5/model.neff index c0073509a8f55293d0d3bfcba3bbf99641faff26..82abb82374c55b8fe514a43f6c684dcf66aa796e 100644 --- a/neuronxcc-2.21.18209.0+043b1bf7/MODULE_a6ac71f9922f4f01abf5+a9d440f5/model.neff +++ b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_a6ac71f9922f4f01abf5+a9d440f5/model.neff @@ -1,3 +1,3 @@ version https://git-lfs.github.com/spec/v1 -oid sha256:bd1ef2067eff59396cb5a741fdbf3492f2ddac863de7a34eaf042bd74be4a42d +oid sha256:c6dba7c62aa41379f9b1362ec08c4a98c7c5a74f1e99be09a8ea6d1a512a7372 size 543744 diff --git a/neuronxcc-2.21.18209.0+043b1bf7/MODULE_a6ac71f9922f4f01abf5+a9d440f5/wrapped_neff.hlo b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_a6ac71f9922f4f01abf5+a9d440f5/wrapped_neff.hlo index b2441c2d8c818a257cab913bf709abc34e489ead..d83acc0dd5b1f73207e5c25238f699191c322b90 100644 --- a/neuronxcc-2.21.18209.0+043b1bf7/MODULE_a6ac71f9922f4f01abf5+a9d440f5/wrapped_neff.hlo +++ b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_a6ac71f9922f4f01abf5+a9d440f5/wrapped_neff.hlo @@ -1,3 +1,3 @@ version https://git-lfs.github.com/spec/v1 -oid sha256:2e873c37f261eb628a038c0c6b418dae07e3f575504d5b6706a5026406dc54fb +oid sha256:8516abb72de6f5c8d2b9ad74508eb524c404b4dbf23acc26daac265ba6925161 size 563380 diff --git a/neuronxcc-2.21.18209.0+043b1bf7/MODULE_b26694c7ca7ec7ec6e04+a9d440f5/model.neff b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_b26694c7ca7ec7ec6e04+a9d440f5/model.neff index 9a259eebc3562c9b81fb654f11e0422ce7e89b0f..757acf24be3a9d8ec5df52a73e520031a1b7069d 100644 --- a/neuronxcc-2.21.18209.0+043b1bf7/MODULE_b26694c7ca7ec7ec6e04+a9d440f5/model.neff +++ b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_b26694c7ca7ec7ec6e04+a9d440f5/model.neff @@ -1,3 +1,3 @@ version https://git-lfs.github.com/spec/v1 -oid sha256:3c9ab01e1069c448e642848435c58af0d2ca04dcd431838e16b957a63a952e1a +oid sha256:1aac12629bb09a3f29593e822adc9258c99737b4f857e6fc1d78284fea075b5d size 277504 diff --git a/neuronxcc-2.21.18209.0+043b1bf7/MODULE_b26694c7ca7ec7ec6e04+a9d440f5/wrapped_neff.hlo b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_b26694c7ca7ec7ec6e04+a9d440f5/wrapped_neff.hlo index f112b02dd57aaeee1702b9a18c2273cf41b6bc6e..d932a4dc0113ea2e873d1acae381acf9064e3b61 100644 --- a/neuronxcc-2.21.18209.0+043b1bf7/MODULE_b26694c7ca7ec7ec6e04+a9d440f5/wrapped_neff.hlo +++ b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_b26694c7ca7ec7ec6e04+a9d440f5/wrapped_neff.hlo @@ -1,3 +1,3 @@ version https://git-lfs.github.com/spec/v1 -oid sha256:331bb9d229be75ef1f6754a79bc020f2388c9c6fdb432a16f6cd667d2b94d4fe +oid sha256:db0772da52a0bb2b152a5ed85c72eb32f7e865604c07c0d0d40db2980016c27c size 285854 diff --git a/neuronxcc-2.21.18209.0+043b1bf7/MODULE_b9a7f9714b4d59f5ca3a+ed72d204/compile_flags.json b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_b9a7f9714b4d59f5ca3a+ed72d204/compile_flags.json new file mode 100644 index 0000000000000000000000000000000000000000..1569eac18fc7f34b3fe66166f2d7a4a59dbc5aa4 --- /dev/null +++ b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_b9a7f9714b4d59f5ca3a+ed72d204/compile_flags.json @@ -0,0 +1 @@ +["--target=trn1", "--auto-cast=none", "--model-type=transformer", "--tensorizer-options=--enable-ccop-compute-overlap --cc-pipeline-tiling-factor=2 --vectorize-strided-dma ", "-O2", "--lnc=1", "--logfile=/tmp/nxd_model/context_encoding_model/_tp0_bk0/log-neuron-cc.txt"] \ No newline at end of file diff --git a/neuronxcc-2.21.18209.0+043b1bf7/MODULE_b9a7f9714b4d59f5ca3a+ed72d204/model.done b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_b9a7f9714b4d59f5ca3a+ed72d204/model.done new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/neuronxcc-2.21.18209.0+043b1bf7/MODULE_b9a7f9714b4d59f5ca3a+ed72d204/model.hlo_module.pb b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_b9a7f9714b4d59f5ca3a+ed72d204/model.hlo_module.pb new file mode 100644 index 0000000000000000000000000000000000000000..97600c8fee203f5d47b26c0361459d35bd50befc --- /dev/null +++ b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_b9a7f9714b4d59f5ca3a+ed72d204/model.hlo_module.pb @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4e9b6aca1e528301e8b70a85f4b3803a2da9a27aa87dee043f72da87c157254a +size 87854 diff --git a/neuronxcc-2.21.18209.0+043b1bf7/MODULE_b9a7f9714b4d59f5ca3a+ed72d204/model.neff b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_b9a7f9714b4d59f5ca3a+ed72d204/model.neff new file mode 100644 index 0000000000000000000000000000000000000000..8fe926df25e08a1231b1d5a7afa708359ac096a6 --- /dev/null +++ b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_b9a7f9714b4d59f5ca3a+ed72d204/model.neff @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:dc532f4b5f8641fae558b9bc2b4047b3d2e1b7c809bc48b06cb2d5b2d6d058e8 +size 400384 diff --git a/neuronxcc-2.21.18209.0+043b1bf7/MODULE_c0a2583211556c96a6a3+a9d440f5/model.neff b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_c0a2583211556c96a6a3+a9d440f5/model.neff index 2cc50cee4905f70e0f7b432779d9f9f7d828880b..56156ccaa5698a6741ceb3f082a2a99df68b33b5 100644 --- a/neuronxcc-2.21.18209.0+043b1bf7/MODULE_c0a2583211556c96a6a3+a9d440f5/model.neff +++ b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_c0a2583211556c96a6a3+a9d440f5/model.neff @@ -1,3 +1,3 @@ version https://git-lfs.github.com/spec/v1 -oid sha256:28c51e6fd4b42e0588441f955581bf23565ed5a879a7e641439ae47272b0d24a +oid sha256:0b61279642ab3f4895869ac9220451ba0253a65848a0ea4cc5f727f78970ff3f size 277504 diff --git a/neuronxcc-2.21.18209.0+043b1bf7/MODULE_c0a2583211556c96a6a3+a9d440f5/wrapped_neff.hlo b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_c0a2583211556c96a6a3+a9d440f5/wrapped_neff.hlo index b789f8bd39b95a57c4083d24d3f45bbee27e8ffb..1766967e3a09d034e0adc5cb4feda25531ea6de0 100644 --- a/neuronxcc-2.21.18209.0+043b1bf7/MODULE_c0a2583211556c96a6a3+a9d440f5/wrapped_neff.hlo +++ b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_c0a2583211556c96a6a3+a9d440f5/wrapped_neff.hlo @@ -1,3 +1,3 @@ version https://git-lfs.github.com/spec/v1 -oid sha256:b6af229fc588092ec7a5e0ac299db07d08f1ef4b72c122bddc478afa3212d6d1 +oid sha256:717b264eed41092c6a186e7596770239039aa71701a44a551fae1b51b3a3fc3a size 289031 diff --git a/neuronxcc-2.21.18209.0+043b1bf7/MODULE_c6450080bc47619254df+ed72d204/model.hlo_module.pb b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_c6450080bc47619254df+ed72d204/model.hlo_module.pb index 03efc635afdb8a697d524a29b6621b77ba97f0b9..0acda2091419ffefac552b387c604242c216e220 100644 --- a/neuronxcc-2.21.18209.0+043b1bf7/MODULE_c6450080bc47619254df+ed72d204/model.hlo_module.pb +++ b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_c6450080bc47619254df+ed72d204/model.hlo_module.pb @@ -1,3 +1,3 @@ version https://git-lfs.github.com/spec/v1 -oid sha256:702e8f63de618809f7d877dbba24bcc8deb1987f3b2fdad4b94a2c0cb91dafd4 +oid sha256:e0209401219006cca96e01930250e97052c586f1267ed95762a3fd065de8cbe9 size 83504 diff --git a/neuronxcc-2.21.18209.0+043b1bf7/MODULE_c6450080bc47619254df+ed72d204/model.neff b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_c6450080bc47619254df+ed72d204/model.neff index fcd584e9dec1b5ba6ee904bc69601adb0c238990..c749246a95d9b4924f615b0fc826a2ffcb3045be 100644 --- a/neuronxcc-2.21.18209.0+043b1bf7/MODULE_c6450080bc47619254df+ed72d204/model.neff +++ b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_c6450080bc47619254df+ed72d204/model.neff @@ -1,3 +1,3 @@ version https://git-lfs.github.com/spec/v1 -oid sha256:686f0112632596b7425a069e7d88002f18a49909ec85304d459874e335339f1e +oid sha256:f3be943131798156033b5df1ddf7aeaa12171fb23e4115c6048429dd50c9ce02 size 328704 diff --git a/neuronxcc-2.21.18209.0+043b1bf7/MODULE_c94bb96d065f690fe53e+a9d440f5/compile_flags.json b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_c94bb96d065f690fe53e+a9d440f5/compile_flags.json new file mode 100644 index 0000000000000000000000000000000000000000..34675115220079309bfad2d45680c478c378a3c0 --- /dev/null +++ b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_c94bb96d065f690fe53e+a9d440f5/compile_flags.json @@ -0,0 +1 @@ +["--target=trn1", "--auto-cast=none", "--model-type=transformer", "--tensorizer-options=--enable-ccop-compute-overlap --cc-pipeline-tiling-factor=2 --vectorize-strided-dma ", "-O2", "--lnc=1", "--logfile=/tmp/nxd_model/token_generation_model/_tp0_bk0/log-neuron-cc.txt", "--enable-internal-neff-wrapper"] \ No newline at end of file diff --git a/neuronxcc-2.21.18209.0+043b1bf7/MODULE_c94bb96d065f690fe53e+a9d440f5/model.done b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_c94bb96d065f690fe53e+a9d440f5/model.done new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/neuronxcc-2.21.18209.0+043b1bf7/MODULE_c94bb96d065f690fe53e+a9d440f5/model.hlo_module.pb b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_c94bb96d065f690fe53e+a9d440f5/model.hlo_module.pb new file mode 100644 index 0000000000000000000000000000000000000000..698710b230a6fb07da4864074d9db31658a3c167 --- /dev/null +++ b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_c94bb96d065f690fe53e+a9d440f5/model.hlo_module.pb @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:33cafc439b5f38f798bffe3f2e760278989d69b241c99e6c0fa0b94b516f46e5 +size 83369 diff --git a/neuronxcc-2.21.18209.0+043b1bf7/MODULE_c94bb96d065f690fe53e+a9d440f5/model.neff b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_c94bb96d065f690fe53e+a9d440f5/model.neff new file mode 100644 index 0000000000000000000000000000000000000000..b8a5c9ce03fa421fb81ff779650cc9712a7e0047 --- /dev/null +++ b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_c94bb96d065f690fe53e+a9d440f5/model.neff @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9166b1cfa64cd9a91d1cb0a3f1d88677bb81d1e14d3bd77bde649045545c44e9 +size 287744 diff --git a/neuronxcc-2.21.18209.0+043b1bf7/MODULE_c94bb96d065f690fe53e+a9d440f5/wrapped_neff.hlo b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_c94bb96d065f690fe53e+a9d440f5/wrapped_neff.hlo new file mode 100644 index 0000000000000000000000000000000000000000..0597f38c8cee14879418917d5b0cbb679fa84ebb --- /dev/null +++ b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_c94bb96d065f690fe53e+a9d440f5/wrapped_neff.hlo @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:93d4938a5f83826a378f86c3a110b11d588bdedbf94557af00d9a13a16bfc7c5 +size 296094 diff --git a/neuronxcc-2.21.18209.0+043b1bf7/MODULE_daf3f26f1dd6b6a7b205/model_index.json b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_daf3f26f1dd6b6a7b205/model_index.json new file mode 100644 index 0000000000000000000000000000000000000000..6e86c661515a0aca4b2f60c5a4738d063ee68cec --- /dev/null +++ b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_daf3f26f1dd6b6a7b205/model_index.json @@ -0,0 +1,25 @@ +{ + "_class_name": "PixArtAlphaPipeline", + "_diffusers_version": "0.35.1", + "_name_or_path": "PixArt-alpha/PixArt-XL-2-512x512", + "scheduler": [ + "diffusers", + "DPMSolverMultistepScheduler" + ], + "text_encoder": [ + "transformers", + "T5EncoderModel" + ], + "tokenizer": [ + "transformers", + "T5Tokenizer" + ], + "transformer": [ + "diffusers", + "PixArtTransformer2DModel" + ], + "vae": [ + "diffusers", + "AutoencoderKL" + ] +} diff --git a/neuronxcc-2.21.18209.0+043b1bf7/MODULE_daf3f26f1dd6b6a7b205/scheduler/scheduler_config.json b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_daf3f26f1dd6b6a7b205/scheduler/scheduler_config.json new file mode 100644 index 0000000000000000000000000000000000000000..dc10f8d63268216248ed744f57d2ff279ee94581 --- /dev/null +++ b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_daf3f26f1dd6b6a7b205/scheduler/scheduler_config.json @@ -0,0 +1,32 @@ +{ + "_class_name": "DPMSolverMultistepScheduler", + "_diffusers_version": "0.35.1", + "algorithm_type": "dpmsolver++", + "beta_end": 0.02, + "beta_schedule": "linear", + "beta_start": 0.0001, + "dynamic_thresholding_ratio": 0.995, + "euler_at_final": false, + "final_sigmas_type": "zero", + "flow_shift": 1.0, + "lambda_min_clipped": -Infinity, + "lower_order_final": true, + "num_train_timesteps": 1000, + "prediction_type": "epsilon", + "rescale_betas_zero_snr": false, + "sample_max_value": 1.0, + "solver_order": 2, + "solver_type": "midpoint", + "steps_offset": 0, + "thresholding": false, + "time_shift_type": "exponential", + "timestep_spacing": "linspace", + "trained_betas": null, + "use_beta_sigmas": false, + "use_dynamic_shifting": false, + "use_exponential_sigmas": false, + "use_flow_sigmas": false, + "use_karras_sigmas": false, + "use_lu_lambdas": false, + "variance_type": null +} diff --git a/neuronxcc-2.21.18209.0+043b1bf7/MODULE_daf3f26f1dd6b6a7b205/text_encoder/config.json b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_daf3f26f1dd6b6a7b205/text_encoder/config.json new file mode 100644 index 0000000000000000000000000000000000000000..cc662b677d536c321eaf2a2b70168cfa739b224e --- /dev/null +++ b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_daf3f26f1dd6b6a7b205/text_encoder/config.json @@ -0,0 +1,52 @@ +{ + "architectures": [ + "T5EncoderModel" + ], + "classifier_dropout": 0.0, + "d_ff": 10240, + "d_kv": 64, + "d_model": 4096, + "decoder_start_token_id": 0, + "dense_act_fn": "gelu_new", + "dropout_rate": 0.1, + "eos_token_id": 1, + "export_model_type": "t5-encoder", + "feed_forward_proj": "gated-gelu", + "initializer_factor": 1.0, + "is_encoder_decoder": false, + "is_gated_act": true, + "layer_norm_epsilon": 1e-06, + "model_type": "t5", + "neuron": { + "auto_cast": null, + "auto_cast_type": null, + "compiler_type": "neuronx-cc", + "compiler_version": "2.21.18209.0+043b1bf7", + "dynamic_batch_size": false, + "float_dtype": "fp32", + "inline_weights_to_neff": false, + "instance_type": "trn1", + "int_dtype": "int64", + "model_type": "t5-encoder", + "optlevel": "2", + "output_attentions": false, + "output_hidden_states": false, + "static_batch_size": 1, + "static_sequence_length": 120, + "task": "feature-extraction", + "tensor_parallel_size": 1 + }, + "num_decoder_layers": 24, + "num_heads": 64, + "num_layers": 24, + "output_past": true, + "pad_token_id": 0, + "relative_attention_max_distance": 128, + "relative_attention_num_buckets": 32, + "tie_word_embeddings": false, + "torch_dtype": "bfloat16", + "torchscript": true, + "transformers_version": "4.55.4", + "use_cache": false, + "vocab_size": 32128 +} diff --git a/neuronxcc-2.21.18209.0+043b1bf7/MODULE_daf3f26f1dd6b6a7b205/text_encoder/model.neuron b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_daf3f26f1dd6b6a7b205/text_encoder/model.neuron new file mode 100644 index 0000000000000000000000000000000000000000..f25c78c3bc1020f4e27ab49b554bae0d0d8e3ae4 --- /dev/null +++ b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_daf3f26f1dd6b6a7b205/text_encoder/model.neuron @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b0ff39f51f7aba7f4c63287ae4f2791ef3f4300f123bbb55f3b6f66b29e24104 +size 9685732433 diff --git a/neuronxcc-2.21.18209.0+043b1bf7/MODULE_daf3f26f1dd6b6a7b205/tokenizer/added_tokens.json b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_daf3f26f1dd6b6a7b205/tokenizer/added_tokens.json new file mode 100644 index 0000000000000000000000000000000000000000..3f5132007c4fcf42b75b65c8b6aa49c7098bcdf4 --- /dev/null +++ b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_daf3f26f1dd6b6a7b205/tokenizer/added_tokens.json @@ -0,0 +1,102 @@ +{ + "": 32099, + "": 32089, + "": 32088, + "": 32087, + "": 32086, + "": 32085, + "": 32084, + "": 32083, + "": 32082, + "": 32081, + "": 32080, + "": 32098, + "": 32079, + "": 32078, + "": 32077, + "": 32076, + "": 32075, + "": 32074, + "": 32073, + "": 32072, + "": 32071, + "": 32070, + "": 32097, + "": 32069, + "": 32068, + "": 32067, + "": 32066, + "": 32065, + "": 32064, + "": 32063, + "": 32062, + "": 32061, + "": 32060, + "": 32096, + "": 32059, + "": 32058, + "": 32057, + "": 32056, + "": 32055, + "": 32054, + "": 32053, + "": 32052, + "": 32051, + "": 32050, + "": 32095, + "": 32049, + "": 32048, + "": 32047, + "": 32046, + "": 32045, + "": 32044, + "": 32043, + "": 32042, + "": 32041, + "": 32040, + "": 32094, + "": 32039, + "": 32038, + "": 32037, + "": 32036, + "": 32035, + "": 32034, + "": 32033, + "": 32032, + "": 32031, + "": 32030, + "": 32093, + "": 32029, + "": 32028, + "": 32027, + "": 32026, + "": 32025, + "": 32024, + "": 32023, + "": 32022, + "": 32021, + "": 32020, + "": 32092, + "": 32019, + "": 32018, + "": 32017, + "": 32016, + "": 32015, + "": 32014, + "": 32013, + "": 32012, + "": 32011, + "": 32010, + "": 32091, + "": 32009, + "": 32008, + "": 32007, + "": 32006, + "": 32005, + "": 32004, + "": 32003, + "": 32002, + "": 32001, + "": 32000, + "": 32090 +} diff --git a/neuronxcc-2.21.18209.0+043b1bf7/MODULE_daf3f26f1dd6b6a7b205/tokenizer/special_tokens_map.json b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_daf3f26f1dd6b6a7b205/tokenizer/special_tokens_map.json new file mode 100644 index 0000000000000000000000000000000000000000..17ade346a1042cbe0c1436f5bedcbd85c099d582 --- /dev/null +++ b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_daf3f26f1dd6b6a7b205/tokenizer/special_tokens_map.json @@ -0,0 +1,125 @@ +{ + "additional_special_tokens": [ + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "" + ], + "eos_token": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false + }, + "pad_token": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false + }, + "unk_token": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false + } +} diff --git a/neuronxcc-2.21.18209.0+043b1bf7/MODULE_daf3f26f1dd6b6a7b205/tokenizer/spiece.model b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_daf3f26f1dd6b6a7b205/tokenizer/spiece.model new file mode 100644 index 0000000000000000000000000000000000000000..317a5ccbde45300f5d1d970d4d449af2108b147e --- /dev/null +++ b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_daf3f26f1dd6b6a7b205/tokenizer/spiece.model @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d60acb128cf7b7f2536e8f38a5b18a05535c9e14c7a355904270e15b0945ea86 +size 791656 diff --git a/neuronxcc-2.21.18209.0+043b1bf7/MODULE_daf3f26f1dd6b6a7b205/tokenizer/tokenizer_config.json b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_daf3f26f1dd6b6a7b205/tokenizer/tokenizer_config.json new file mode 100644 index 0000000000000000000000000000000000000000..ddb6837b61620d0c17e8742b2a06f83ee4063ae1 --- /dev/null +++ b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_daf3f26f1dd6b6a7b205/tokenizer/tokenizer_config.json @@ -0,0 +1,941 @@ +{ + "add_prefix_space": true, + "added_tokens_decoder": { + "0": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "1": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "2": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32000": { + "content": "", + "lstrip": true, + "normalized": false, + "rstrip": true, + "single_word": true, + "special": true + }, + "32001": { + "content": "", + "lstrip": true, + "normalized": false, + "rstrip": true, + "single_word": true, + "special": true + }, + "32002": { + "content": "", + "lstrip": true, + "normalized": false, + "rstrip": true, + "single_word": true, + "special": true + }, + "32003": { + "content": "", + "lstrip": true, + "normalized": false, + "rstrip": true, + "single_word": true, + "special": true + }, + "32004": { + "content": "", + "lstrip": true, + "normalized": false, + "rstrip": true, + "single_word": true, + "special": true + }, + "32005": { + "content": "", + "lstrip": true, + "normalized": false, + "rstrip": true, + "single_word": true, + "special": true + }, + "32006": { + "content": "", + "lstrip": true, + "normalized": false, + "rstrip": true, + "single_word": true, + "special": true + }, + "32007": { + "content": "", + "lstrip": true, + "normalized": false, + "rstrip": true, + "single_word": true, + "special": true + }, + "32008": { + "content": "", + "lstrip": true, + "normalized": false, + "rstrip": true, + "single_word": true, + "special": true + }, + "32009": { + "content": "", + "lstrip": true, + "normalized": false, + "rstrip": true, + "single_word": true, + "special": true + }, + "32010": { + "content": "", + "lstrip": true, + "normalized": false, + "rstrip": true, + "single_word": true, + "special": true + }, + "32011": { + "content": "", + "lstrip": true, + "normalized": false, + "rstrip": true, + "single_word": true, + "special": true + }, + "32012": { + "content": "", + "lstrip": true, + "normalized": false, + "rstrip": true, + "single_word": true, + "special": true + }, + "32013": { + "content": "", + "lstrip": true, + "normalized": false, + "rstrip": true, + "single_word": true, + "special": true + }, + "32014": { + "content": "", + "lstrip": true, + "normalized": false, + "rstrip": true, + "single_word": true, + "special": true + }, + "32015": { + "content": "", + "lstrip": true, + "normalized": false, + "rstrip": true, + "single_word": true, + "special": true + }, + "32016": { + "content": "", + "lstrip": true, + "normalized": false, + "rstrip": true, + "single_word": true, + "special": true + }, + "32017": { + "content": "", + "lstrip": true, + "normalized": false, + "rstrip": true, + "single_word": true, + "special": true + }, + "32018": { + "content": "", + "lstrip": true, + "normalized": false, + "rstrip": true, + "single_word": true, + "special": true + }, + "32019": { + "content": "", + "lstrip": true, + "normalized": false, + "rstrip": true, + "single_word": true, + "special": true + }, + "32020": { + "content": "", + "lstrip": true, + "normalized": false, + "rstrip": true, + "single_word": true, + "special": true + }, + "32021": { + "content": "", + "lstrip": true, + "normalized": false, + "rstrip": true, + "single_word": true, + "special": true + }, + "32022": { + "content": "", + "lstrip": true, + "normalized": false, + "rstrip": true, + "single_word": true, + "special": true + }, + "32023": { + "content": "", + "lstrip": true, + "normalized": false, + "rstrip": true, + "single_word": true, + "special": true + }, + "32024": { + "content": "", + "lstrip": true, + "normalized": false, + "rstrip": true, + "single_word": true, + "special": true + }, + "32025": { + "content": "", + "lstrip": true, + "normalized": false, + "rstrip": true, + "single_word": true, + "special": true + }, + "32026": { + "content": "", + "lstrip": true, + "normalized": false, + "rstrip": true, + "single_word": true, + "special": true + }, + "32027": { + "content": "", + "lstrip": true, + "normalized": false, + "rstrip": true, + "single_word": true, + "special": true + }, + "32028": { + "content": "", + "lstrip": true, + "normalized": false, + "rstrip": true, + "single_word": true, + "special": true + }, + "32029": { + "content": "", + "lstrip": true, + "normalized": false, + "rstrip": true, + "single_word": true, + "special": true + }, + "32030": { + "content": "", + "lstrip": true, + "normalized": false, + "rstrip": true, + "single_word": true, + "special": true + }, + "32031": { + "content": "", + "lstrip": true, + "normalized": false, + "rstrip": true, + "single_word": true, + "special": true + }, + "32032": { + "content": "", + "lstrip": true, + "normalized": false, + "rstrip": true, + "single_word": true, + "special": true + }, + "32033": { + "content": "", + "lstrip": true, + "normalized": false, + "rstrip": true, + "single_word": true, + "special": true + }, + "32034": { + "content": "", + "lstrip": true, + "normalized": false, + "rstrip": true, + "single_word": true, + "special": true + }, + "32035": { + "content": "", + "lstrip": true, + "normalized": false, + "rstrip": true, + "single_word": true, + "special": true + }, + "32036": { + "content": "", + "lstrip": true, + "normalized": false, + "rstrip": true, + "single_word": true, + "special": true + }, + "32037": { + "content": "", + "lstrip": true, + "normalized": false, + "rstrip": true, + "single_word": true, + "special": true + }, + "32038": { + "content": "", + "lstrip": true, + "normalized": false, + "rstrip": true, + "single_word": true, + "special": true + }, + "32039": { + "content": "", + "lstrip": true, + "normalized": false, + "rstrip": true, + "single_word": true, + "special": true + }, + "32040": { + "content": "", + "lstrip": true, + "normalized": false, + "rstrip": true, + "single_word": true, + "special": true + }, + "32041": { + "content": "", + "lstrip": true, + "normalized": false, + "rstrip": true, + "single_word": true, + "special": true + }, + "32042": { + "content": "", + "lstrip": true, + "normalized": false, + "rstrip": true, + "single_word": true, + "special": true + }, + "32043": { + "content": "", + "lstrip": true, + "normalized": false, + "rstrip": true, + "single_word": true, + "special": true + }, + "32044": { + "content": "", + "lstrip": true, + "normalized": false, + "rstrip": true, + "single_word": true, + "special": true + }, + "32045": { + "content": "", + "lstrip": true, + "normalized": false, + "rstrip": true, + "single_word": true, + "special": true + }, + "32046": { + "content": "", + "lstrip": true, + "normalized": false, + "rstrip": true, + "single_word": true, + "special": true + }, + "32047": { + "content": "", + "lstrip": true, + "normalized": false, + "rstrip": true, + "single_word": true, + "special": true + }, + "32048": { + "content": "", + "lstrip": true, + "normalized": false, + "rstrip": true, + "single_word": true, + "special": true + }, + "32049": { + "content": "", + "lstrip": true, + "normalized": false, + "rstrip": true, + "single_word": true, + "special": true + }, + "32050": { + "content": "", + "lstrip": true, + "normalized": false, + "rstrip": true, + "single_word": true, + "special": true + }, + "32051": { + "content": "", + "lstrip": true, + "normalized": false, + "rstrip": true, + "single_word": true, + "special": true + }, + "32052": { + "content": "", + "lstrip": true, + "normalized": false, + "rstrip": true, + "single_word": true, + "special": true + }, + "32053": { + "content": "", + "lstrip": true, + "normalized": false, + "rstrip": true, + "single_word": true, + "special": true + }, + "32054": { + "content": "", + "lstrip": true, + "normalized": false, + "rstrip": true, + "single_word": true, + "special": true + }, + "32055": { + "content": "", + "lstrip": true, + "normalized": false, + "rstrip": true, + "single_word": true, + "special": true + }, + "32056": { + "content": "", + "lstrip": true, + "normalized": false, + "rstrip": true, + "single_word": true, + "special": true + }, + "32057": { + "content": "", + "lstrip": true, + "normalized": false, + "rstrip": true, + "single_word": true, + "special": true + }, + "32058": { + "content": "", + "lstrip": true, + "normalized": false, + "rstrip": true, + "single_word": true, + "special": true + }, + "32059": { + "content": "", + "lstrip": true, + "normalized": false, + "rstrip": true, + "single_word": true, + "special": true + }, + "32060": { + "content": "", + "lstrip": true, + "normalized": false, + "rstrip": true, + "single_word": true, + "special": true + }, + "32061": { + "content": "", + "lstrip": true, + "normalized": false, + "rstrip": true, + "single_word": true, + "special": true + }, + "32062": { + "content": "", + "lstrip": true, + "normalized": false, + "rstrip": true, + "single_word": true, + "special": true + }, + "32063": { + "content": "", + "lstrip": true, + "normalized": false, + "rstrip": true, + "single_word": true, + "special": true + }, + "32064": { + "content": "", + "lstrip": true, + "normalized": false, + "rstrip": true, + "single_word": true, + "special": true + }, + "32065": { + "content": "", + "lstrip": true, + "normalized": false, + "rstrip": true, + "single_word": true, + "special": true + }, + "32066": { + "content": "", + "lstrip": true, + "normalized": false, + "rstrip": true, + "single_word": true, + "special": true + }, + "32067": { + "content": "", + "lstrip": true, + "normalized": false, + "rstrip": true, + "single_word": true, + "special": true + }, + "32068": { + "content": "", + "lstrip": true, + "normalized": false, + "rstrip": true, + "single_word": true, + "special": true + }, + "32069": { + "content": "", + "lstrip": true, + "normalized": false, + "rstrip": true, + "single_word": true, + "special": true + }, + "32070": { + "content": "", + "lstrip": true, + "normalized": false, + "rstrip": true, + "single_word": true, + "special": true + }, + "32071": { + "content": "", + "lstrip": true, + "normalized": false, + "rstrip": true, + "single_word": true, + "special": true + }, + "32072": { + "content": "", + "lstrip": true, + "normalized": false, + "rstrip": true, + "single_word": true, + "special": true + }, + "32073": { + "content": "", + "lstrip": true, + "normalized": false, + "rstrip": true, + "single_word": true, + "special": true + }, + "32074": { + "content": "", + "lstrip": true, + "normalized": false, + "rstrip": true, + "single_word": true, + "special": true + }, + "32075": { + "content": "", + "lstrip": true, + "normalized": false, + "rstrip": true, + "single_word": true, + "special": true + }, + "32076": { + "content": "", + "lstrip": true, + "normalized": false, + "rstrip": true, + "single_word": true, + "special": true + }, + "32077": { + "content": "", + "lstrip": true, + "normalized": false, + "rstrip": true, + "single_word": true, + "special": true + }, + "32078": { + "content": "", + "lstrip": true, + "normalized": false, + "rstrip": true, + "single_word": true, + "special": true + }, + "32079": { + "content": "", + "lstrip": true, + "normalized": false, + "rstrip": true, + "single_word": true, + "special": true + }, + "32080": { + "content": "", + "lstrip": true, + "normalized": false, + "rstrip": true, + "single_word": true, + "special": true + }, + "32081": { + "content": "", + "lstrip": true, + "normalized": false, + "rstrip": true, + "single_word": true, + "special": true + }, + "32082": { + "content": "", + "lstrip": true, + "normalized": false, + "rstrip": true, + "single_word": true, + "special": true + }, + "32083": { + "content": "", + "lstrip": true, + "normalized": false, + "rstrip": true, + "single_word": true, + "special": true + }, + "32084": { + "content": "", + "lstrip": true, + "normalized": false, + "rstrip": true, + "single_word": true, + "special": true + }, + "32085": { + "content": "", + "lstrip": true, + "normalized": false, + "rstrip": true, + "single_word": true, + "special": true + }, + "32086": { + "content": "", + "lstrip": true, + "normalized": false, + "rstrip": true, + "single_word": true, + "special": true + }, + "32087": { + "content": "", + "lstrip": true, + "normalized": false, + "rstrip": true, + "single_word": true, + "special": true + }, + "32088": { + "content": "", + "lstrip": true, + "normalized": false, + "rstrip": true, + "single_word": true, + "special": true + }, + "32089": { + "content": "", + "lstrip": true, + "normalized": false, + "rstrip": true, + "single_word": true, + "special": true + }, + "32090": { + "content": "", + "lstrip": true, + "normalized": false, + "rstrip": true, + "single_word": true, + "special": true + }, + "32091": { + "content": "", + "lstrip": true, + "normalized": false, + "rstrip": true, + "single_word": true, + "special": true + }, + "32092": { + "content": "", + "lstrip": true, + "normalized": false, + "rstrip": true, + "single_word": true, + "special": true + }, + "32093": { + "content": "", + "lstrip": true, + "normalized": false, + "rstrip": true, + "single_word": true, + "special": true + }, + "32094": { + "content": "", + "lstrip": true, + "normalized": false, + "rstrip": true, + "single_word": true, + "special": true + }, + "32095": { + "content": "", + "lstrip": true, + "normalized": false, + "rstrip": true, + "single_word": true, + "special": true + }, + "32096": { + "content": "", + "lstrip": true, + "normalized": false, + "rstrip": true, + "single_word": true, + "special": true + }, + "32097": { + "content": "", + "lstrip": true, + "normalized": false, + "rstrip": true, + "single_word": true, + "special": true + }, + "32098": { + "content": "", + "lstrip": true, + "normalized": false, + "rstrip": true, + "single_word": true, + "special": true + }, + "32099": { + "content": "", + "lstrip": true, + "normalized": false, + "rstrip": true, + "single_word": true, + "special": true + } + }, + "additional_special_tokens": [ + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "", + "" + ], + "clean_up_tokenization_spaces": true, + "eos_token": "", + "extra_ids": 100, + "extra_special_tokens": {}, + "legacy": true, + "model_max_length": 512, + "pad_token": "", + "sp_model_kwargs": {}, + "tokenizer_class": "T5Tokenizer", + "unk_token": "" +} diff --git a/neuronxcc-2.21.18209.0+043b1bf7/MODULE_daf3f26f1dd6b6a7b205/transformer/config.json b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_daf3f26f1dd6b6a7b205/transformer/config.json new file mode 100644 index 0000000000000000000000000000000000000000..a2aa62420b2583f707a250fd12b4a01cb278ab27 --- /dev/null +++ b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_daf3f26f1dd6b6a7b205/transformer/config.json @@ -0,0 +1,59 @@ +{ + "_class_name": "PixArtTransformer2DModel", + "_diffusers_version": "0.35.1", + "_use_default_values": [ + "interpolation_scale", + "use_additional_conditions" + ], + "activation_fn": "gelu-approximate", + "attention_bias": true, + "attention_head_dim": 72, + "attention_type": "default", + "caption_channels": 4096, + "cross_attention_dim": 1152, + "double_self_attention": false, + "dropout": 0.0, + "in_channels": 4, + "interpolation_scale": null, + "neuron": { + "auto_cast": null, + "auto_cast_type": null, + "compiler_type": "neuronx-cc", + "compiler_version": "2.21.18209.0+043b1bf7", + "dynamic_batch_size": false, + "float_dtype": "bf16", + "inline_weights_to_neff": false, + "instance_type": "trn1", + "int_dtype": "int64", + "model_type": "pixart-transformer-2d", + "optlevel": "2", + "output_attentions": false, + "output_hidden_states": false, + "static_batch_size": 1, + "static_encoder_hidden_size": 4096, + "static_height": 64, + "static_num_channels": 4, + "static_sequence_length": 120, + "static_vae_scale_factor": 8, + "static_width": 64, + "task": "semantic-segmentation", + "tensor_parallel_size": 1 + }, + "norm_elementwise_affine": false, + "norm_eps": 1e-06, + "norm_num_groups": 32, + "norm_type": "ada_norm_single", + "num_attention_heads": 16, + "num_embeds_ada_norm": 1000, + "num_layers": 28, + "num_vector_embeds": null, + "only_cross_attention": false, + "out_channels": 8, + "output_attentions": false, + "patch_size": 2, + "sample_size": 64, + "transformers_version": null, + "upcast_attention": false, + "use_additional_conditions": null, + "use_linear_projection": false +} diff --git a/neuronxcc-2.21.18209.0+043b1bf7/MODULE_daf3f26f1dd6b6a7b205/transformer/model.neuron b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_daf3f26f1dd6b6a7b205/transformer/model.neuron new file mode 100644 index 0000000000000000000000000000000000000000..c2b84262279cfa2e53f44a3a2eef330410a329fe --- /dev/null +++ b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_daf3f26f1dd6b6a7b205/transformer/model.neuron @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e32f3b72a541eb7a4843f56c82e36e6627333e0db4716acfdd10c0db34c6ca16 +size 1297774620 diff --git a/neuronxcc-2.21.18209.0+043b1bf7/MODULE_daf3f26f1dd6b6a7b205/vae_decoder/config.json b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_daf3f26f1dd6b6a7b205/vae_decoder/config.json new file mode 100644 index 0000000000000000000000000000000000000000..b4d0cd98eb178deefb817a473bb4a771cde8fca0 --- /dev/null +++ b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_daf3f26f1dd6b6a7b205/vae_decoder/config.json @@ -0,0 +1,68 @@ +{ + "_class_name": "AutoencoderKL", + "_diffusers_version": "0.35.1", + "_use_default_values": [ + "shift_factor", + "latents_mean", + "mid_block_add_attention", + "latents_std", + "use_post_quant_conv", + "use_quant_conv" + ], + "act_fn": "silu", + "block_out_channels": [ + 128, + 256, + 512, + 512 + ], + "down_block_types": [ + "DownEncoderBlock2D", + "DownEncoderBlock2D", + "DownEncoderBlock2D", + "DownEncoderBlock2D" + ], + "force_upcast": true, + "in_channels": 3, + "latent_channels": 4, + "latents_mean": null, + "latents_std": null, + "layers_per_block": 2, + "mid_block_add_attention": true, + "neuron": { + "auto_cast": null, + "auto_cast_type": null, + "compiler_type": "neuronx-cc", + "compiler_version": "2.21.18209.0+043b1bf7", + "dynamic_batch_size": false, + "float_dtype": "bf16", + "inline_weights_to_neff": false, + "instance_type": "trn1", + "int_dtype": "int64", + "model_type": "vae-decoder", + "optlevel": "2", + "output_attentions": false, + "output_hidden_states": false, + "static_batch_size": 1, + "static_height": 64, + "static_num_channels": 4, + "static_width": 64, + "task": "semantic-segmentation", + "tensor_parallel_size": 1 + }, + "norm_num_groups": 32, + "out_channels": 3, + "output_attentions": false, + "sample_size": 256, + "scaling_factor": 0.18215, + "shift_factor": null, + "transformers_version": null, + "up_block_types": [ + "UpDecoderBlock2D", + "UpDecoderBlock2D", + "UpDecoderBlock2D", + "UpDecoderBlock2D" + ], + "use_post_quant_conv": true, + "use_quant_conv": true +} diff --git a/neuronxcc-2.21.18209.0+043b1bf7/MODULE_daf3f26f1dd6b6a7b205/vae_decoder/model.neuron b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_daf3f26f1dd6b6a7b205/vae_decoder/model.neuron new file mode 100644 index 0000000000000000000000000000000000000000..8a045bc2c6b6cdc5dea169eb7e6a27c3ab28b29d --- /dev/null +++ b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_daf3f26f1dd6b6a7b205/vae_decoder/model.neuron @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:993c563874745eddc8f24468684045cfce05eb4cbc877d2c7c296209d5944984 +size 311513621 diff --git a/neuronxcc-2.21.18209.0+043b1bf7/MODULE_daf3f26f1dd6b6a7b205/vae_encoder/config.json b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_daf3f26f1dd6b6a7b205/vae_encoder/config.json new file mode 100644 index 0000000000000000000000000000000000000000..a09c449fd1641597db1bd8b2559b322ecfa43510 --- /dev/null +++ b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_daf3f26f1dd6b6a7b205/vae_encoder/config.json @@ -0,0 +1,68 @@ +{ + "_class_name": "AutoencoderKL", + "_diffusers_version": "0.35.1", + "_use_default_values": [ + "shift_factor", + "latents_mean", + "mid_block_add_attention", + "latents_std", + "use_post_quant_conv", + "use_quant_conv" + ], + "act_fn": "silu", + "block_out_channels": [ + 128, + 256, + 512, + 512 + ], + "down_block_types": [ + "DownEncoderBlock2D", + "DownEncoderBlock2D", + "DownEncoderBlock2D", + "DownEncoderBlock2D" + ], + "force_upcast": true, + "in_channels": 3, + "latent_channels": 4, + "latents_mean": null, + "latents_std": null, + "layers_per_block": 2, + "mid_block_add_attention": true, + "neuron": { + "auto_cast": null, + "auto_cast_type": null, + "compiler_type": "neuronx-cc", + "compiler_version": "2.21.18209.0+043b1bf7", + "dynamic_batch_size": false, + "float_dtype": "fp32", + "inline_weights_to_neff": false, + "instance_type": "trn1", + "int_dtype": "int64", + "model_type": "vae-encoder", + "optlevel": "2", + "output_attentions": false, + "output_hidden_states": false, + "static_batch_size": 1, + "static_height": 512, + "static_num_channels": 3, + "static_width": 512, + "task": "semantic-segmentation", + "tensor_parallel_size": 1 + }, + "norm_num_groups": 32, + "out_channels": 3, + "output_attentions": false, + "sample_size": 256, + "scaling_factor": 0.18215, + "shift_factor": null, + "transformers_version": null, + "up_block_types": [ + "UpDecoderBlock2D", + "UpDecoderBlock2D", + "UpDecoderBlock2D", + "UpDecoderBlock2D" + ], + "use_post_quant_conv": true, + "use_quant_conv": true +} diff --git a/neuronxcc-2.21.18209.0+043b1bf7/MODULE_daf3f26f1dd6b6a7b205/vae_encoder/model.neuron b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_daf3f26f1dd6b6a7b205/vae_encoder/model.neuron new file mode 100644 index 0000000000000000000000000000000000000000..843a0f66fea7574b5f05bd2b77d3e63fa6f7060c --- /dev/null +++ b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_daf3f26f1dd6b6a7b205/vae_encoder/model.neuron @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a2b5a96f3de64077427b802f938d7567cd75325327c59dcde903d3c8a636c17c +size 189176531 diff --git a/neuronxcc-2.21.18209.0+043b1bf7/MODULE_e1858108239cd6fa94e5+34ec65ed/compile_flags.json b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_e1858108239cd6fa94e5+34ec65ed/compile_flags.json new file mode 100644 index 0000000000000000000000000000000000000000..0f9fcd7f2e8677b28f74e732e495a2328b426166 --- /dev/null +++ b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_e1858108239cd6fa94e5+34ec65ed/compile_flags.json @@ -0,0 +1 @@ +["--target=trn1", "--enable-saturate-infinity", "--auto-cast=none", "--model-type=transformer", "-O1", "--logfile=/tmp/nxdi_test_4526f6f2-02bb-438a-9754-b84303128137/compiler_workdir/AttentionModelWrapper/_tp0_bk0/log-neuron-cc.txt", "--enable-internal-neff-wrapper"] \ No newline at end of file diff --git a/neuronxcc-2.21.18209.0+043b1bf7/MODULE_e1858108239cd6fa94e5+34ec65ed/model.done b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_e1858108239cd6fa94e5+34ec65ed/model.done new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/neuronxcc-2.21.18209.0+043b1bf7/MODULE_e1858108239cd6fa94e5+34ec65ed/model.hlo_module.pb b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_e1858108239cd6fa94e5+34ec65ed/model.hlo_module.pb new file mode 100644 index 0000000000000000000000000000000000000000..a11cc062167102b0f4faa9fdf16388d72d9e0015 --- /dev/null +++ b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_e1858108239cd6fa94e5+34ec65ed/model.hlo_module.pb @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4590b82eb167fd46963abdbb717cc18cb9511961a3393d100eeacdbdc45b0243 +size 11280 diff --git a/neuronxcc-2.21.18209.0+043b1bf7/MODULE_e1858108239cd6fa94e5+34ec65ed/model.neff b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_e1858108239cd6fa94e5+34ec65ed/model.neff new file mode 100644 index 0000000000000000000000000000000000000000..6717d5ad8936117a6024cc6896bafe8dbf23c164 --- /dev/null +++ b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_e1858108239cd6fa94e5+34ec65ed/model.neff @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:776065fdd2530e62f34fe5457be745c64d23e7879bcc59a4410dae10b544e336 +size 1444864 diff --git a/neuronxcc-2.21.18209.0+043b1bf7/MODULE_e1858108239cd6fa94e5+34ec65ed/wrapped_neff.hlo b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_e1858108239cd6fa94e5+34ec65ed/wrapped_neff.hlo new file mode 100644 index 0000000000000000000000000000000000000000..a3adc0f1122696300f11a7814379929176e35d54 --- /dev/null +++ b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_e1858108239cd6fa94e5+34ec65ed/wrapped_neff.hlo @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:173943c3ef880f2c453a013aab71d45250d6f91eb4f9e2607d435d99e8392b6a +size 1447845 diff --git a/neuronxcc-2.21.18209.0+043b1bf7/MODULE_e7bf36a5a3a95f1e548a+a9d440f5/model.neff b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_e7bf36a5a3a95f1e548a+a9d440f5/model.neff index 6e98350acfd931d10a9169dac6ec483b457402e9..63bf496eb607784c0e8506e2b735ee208526d3f0 100644 --- a/neuronxcc-2.21.18209.0+043b1bf7/MODULE_e7bf36a5a3a95f1e548a+a9d440f5/model.neff +++ b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_e7bf36a5a3a95f1e548a+a9d440f5/model.neff @@ -1,3 +1,3 @@ version https://git-lfs.github.com/spec/v1 -oid sha256:5943d9d378336de05e95bf60d9fffcbba967bb61aa896d7c2d57d7cea99ba3b1 +oid sha256:bce5e959b8b423ae1f3d90425e5bf6e8b650943e80f178dcae24c9822386cc2a size 216064 diff --git a/neuronxcc-2.21.18209.0+043b1bf7/MODULE_e7bf36a5a3a95f1e548a+a9d440f5/wrapped_neff.hlo b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_e7bf36a5a3a95f1e548a+a9d440f5/wrapped_neff.hlo index bcfcd1df8c994adf3df19a47280fd7c17f2cc94c..f22e21d74c5cd9512e07747f147570fc77878600 100644 --- a/neuronxcc-2.21.18209.0+043b1bf7/MODULE_e7bf36a5a3a95f1e548a+a9d440f5/wrapped_neff.hlo +++ b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_e7bf36a5a3a95f1e548a+a9d440f5/wrapped_neff.hlo @@ -1,3 +1,3 @@ version https://git-lfs.github.com/spec/v1 -oid sha256:4ee253742755fc0770c0d9b7b935c83413df6e4b78624bcf9fb29670e5ac6100 +oid sha256:00a95fe8dafa968bb5e4852ffddd4f721b765275db7a6a3d53c2ffadb6c27e04 size 224412 diff --git a/neuronxcc-2.21.18209.0+043b1bf7/MODULE_ec01adc6d76b4d3733bc+cdc6a67b/compile_flags.json b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_ec01adc6d76b4d3733bc+cdc6a67b/compile_flags.json new file mode 100644 index 0000000000000000000000000000000000000000..d49cd34bbe7d1fdd103cc8fe415dedf9d8e74aa6 --- /dev/null +++ b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_ec01adc6d76b4d3733bc+cdc6a67b/compile_flags.json @@ -0,0 +1 @@ +["--target=trn1", "--enable-saturate-infinity", "--auto-cast=none", "--model-type=transformer", "-O1", "--logfile=/tmp/nxdi_test_268d0856-709b-437d-b975-33e1027cf2ad/compiler_workdir/AttentionModelWrapper/_tp0_bk0/log-neuron-cc.txt", "--enable-internal-neff-wrapper"] \ No newline at end of file diff --git a/neuronxcc-2.21.18209.0+043b1bf7/MODULE_ec01adc6d76b4d3733bc+cdc6a67b/model.done b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_ec01adc6d76b4d3733bc+cdc6a67b/model.done new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/neuronxcc-2.21.18209.0+043b1bf7/MODULE_ec01adc6d76b4d3733bc+cdc6a67b/model.hlo_module.pb b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_ec01adc6d76b4d3733bc+cdc6a67b/model.hlo_module.pb new file mode 100644 index 0000000000000000000000000000000000000000..8496781848c02ecd308b5b2c5a3c342b702425e7 --- /dev/null +++ b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_ec01adc6d76b4d3733bc+cdc6a67b/model.hlo_module.pb @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:51e79a5cc325f9a317d158d931d75ec73ae1cfb16a4d83343a2593edd95d0044 +size 8979 diff --git a/neuronxcc-2.21.18209.0+043b1bf7/MODULE_ec01adc6d76b4d3733bc+cdc6a67b/model.neff b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_ec01adc6d76b4d3733bc+cdc6a67b/model.neff new file mode 100644 index 0000000000000000000000000000000000000000..ecf15ede3585ad81042bd80306594b0f35402eeb --- /dev/null +++ b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_ec01adc6d76b4d3733bc+cdc6a67b/model.neff @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7560c529a21e8e694056394037c0dc371f69ddadf6e871d101a5390b8ab270c1 +size 246784 diff --git a/neuronxcc-2.21.18209.0+043b1bf7/MODULE_ec01adc6d76b4d3733bc+cdc6a67b/wrapped_neff.hlo b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_ec01adc6d76b4d3733bc+cdc6a67b/wrapped_neff.hlo new file mode 100644 index 0000000000000000000000000000000000000000..2081fc83059f576c3713a45041eaefcccafb3483 --- /dev/null +++ b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_ec01adc6d76b4d3733bc+cdc6a67b/wrapped_neff.hlo @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6ed133e6bd44a6145d58ed324ebe97ee174d2231948878fd543d6ab0a0a3ef5a +size 249608 diff --git a/neuronxcc-2.21.18209.0+043b1bf7/MODULE_f4ada83ccf930dab43a6+cd3419b6/model.neff b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_f4ada83ccf930dab43a6+cd3419b6/model.neff index 31d738c2701dc98d79a2514e966a745dd8b729d2..ae865be9b374885c2fc48ad4210998bfa5b31822 100644 --- a/neuronxcc-2.21.18209.0+043b1bf7/MODULE_f4ada83ccf930dab43a6+cd3419b6/model.neff +++ b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_f4ada83ccf930dab43a6+cd3419b6/model.neff @@ -1,3 +1,3 @@ version https://git-lfs.github.com/spec/v1 -oid sha256:f91f97e7f1e0eb2e3a81af5cfdda2846eb1c478d3cb6679b5a13673c1b083779 +oid sha256:f541888df5d30c3d67a56163a1068c3692ee9ada874e678ab7254fb51af0cfeb size 369664 diff --git a/neuronxcc-2.21.18209.0+043b1bf7/MODULE_f4ada83ccf930dab43a6+cd3419b6/wrapped_neff.hlo b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_f4ada83ccf930dab43a6+cd3419b6/wrapped_neff.hlo index 3c327e8b7a9c8316d0d8764ee5fdf90390d44bc6..97aa5f33bb794c16f3aa9b236b2190d234e0990d 100644 --- a/neuronxcc-2.21.18209.0+043b1bf7/MODULE_f4ada83ccf930dab43a6+cd3419b6/wrapped_neff.hlo +++ b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_f4ada83ccf930dab43a6+cd3419b6/wrapped_neff.hlo @@ -1,3 +1,3 @@ version https://git-lfs.github.com/spec/v1 -oid sha256:2f614c1ccf7dbd3c6233daa1397fb4fdd5a582e8652cfb558f624a9207397ade +oid sha256:a7c7e5a9a1208751581b37d797ce8d5b5e52f19f045eb31cd2ca6f5149d7c038 size 379362 diff --git a/neuronxcc-2.21.18209.0+043b1bf7/MODULE_fc37bb64f7e86324075c+ed72d204/model.hlo_module.pb b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_fc37bb64f7e86324075c+ed72d204/model.hlo_module.pb index 1ec6b6f23c3d2c9a5270175a4551b84156d1709d..a291eef6371ee0cd154490c84b4b4979190709b3 100644 --- a/neuronxcc-2.21.18209.0+043b1bf7/MODULE_fc37bb64f7e86324075c+ed72d204/model.hlo_module.pb +++ b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_fc37bb64f7e86324075c+ed72d204/model.hlo_module.pb @@ -1,3 +1,3 @@ version https://git-lfs.github.com/spec/v1 -oid sha256:72f0d62073d2232a9bc3726e5abccdbf25665abb7f30afbc8bb52715c47072de +oid sha256:df5b9b5d719971d47dec5dcb4d4b5bf90ec5f188bf96403d9ef0053c49d97724 size 82772 diff --git a/neuronxcc-2.21.18209.0+043b1bf7/MODULE_fc37bb64f7e86324075c+ed72d204/model.neff b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_fc37bb64f7e86324075c+ed72d204/model.neff index 54b7c31b59ac4e91b1b2904544ba323e806306ec..c67c004fd985288462c0ef18268b717def94acea 100644 --- a/neuronxcc-2.21.18209.0+043b1bf7/MODULE_fc37bb64f7e86324075c+ed72d204/model.neff +++ b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_fc37bb64f7e86324075c+ed72d204/model.neff @@ -1,3 +1,3 @@ version https://git-lfs.github.com/spec/v1 -oid sha256:ac4789ef9720aeb2b286738fed1312386b222abee4a80251f9b958057d01ad17 +oid sha256:b9572352e721af4c0c3a2c56e76a4b5ab2ae9605d4829aea3fe819b4329163be size 267264 diff --git a/neuronxcc-2.21.18209.0+043b1bf7/MODULE_fef991cead1748c4d101+ed72d204/model.hlo_module.pb b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_fef991cead1748c4d101+ed72d204/model.hlo_module.pb index c38a882941e556e4154d326b537b164fc53165ba..d7ac504dad1ca324a321baa4d7ed0d98d9e0079b 100644 --- a/neuronxcc-2.21.18209.0+043b1bf7/MODULE_fef991cead1748c4d101+ed72d204/model.hlo_module.pb +++ b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_fef991cead1748c4d101+ed72d204/model.hlo_module.pb @@ -1,3 +1,3 @@ version https://git-lfs.github.com/spec/v1 -oid sha256:2367c7833b0446bd03675e500d6693feea1595aa1b28a3d570e452ee0605eb16 +oid sha256:fed0bc9e6a1063940352f77cf3c69fd69dfe037f37ff904cce52c6b300a4a81a size 694128 diff --git a/neuronxcc-2.21.18209.0+043b1bf7/MODULE_fef991cead1748c4d101+ed72d204/model.neff b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_fef991cead1748c4d101+ed72d204/model.neff index a68deb2e3d6e6f5ad77d808e99b0a2db7d326b32..bccd5738420a9038361bde5e17daf9b65b46e23a 100644 --- a/neuronxcc-2.21.18209.0+043b1bf7/MODULE_fef991cead1748c4d101+ed72d204/model.neff +++ b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_fef991cead1748c4d101+ed72d204/model.neff @@ -1,3 +1,3 @@ version https://git-lfs.github.com/spec/v1 -oid sha256:2d3d159150006bfdbc711580c030408e231ab5b3026fa03dbe16b24437e221ba +oid sha256:a99aac18d392a7fa78c603ee2eaa429959a523455a432a6bbb186be4711f1396 size 625664